def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False, name='global_step')
# Get images and labels for CIFAR-10.
images, labels, names = drd.distorted_inputs()
# # Build an initialization operation to run below.
init = tf.global_variables_initializer()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
names_list = []
start_time = time.time()
for i in range(0, 20000):
if i % 1000 == 0:
print(i)
names_im = sess.run([names])
names_list.append(names_im)
names = np.vstack(names_list).flatten()
#print(names)
print(type(names))
print(names.shape)
print(np.unique(names, return_counts=True))
uniq, counts = np.unique(names, return_counts=True)
print(uniq.shape)
print(counts.shape)
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False, name='global_step')
# Get images and labels for CIFAR-10.
images, labels, names = drd.distorted_inputs()
#get validation data
val_images, val_labels = drd.inputs(True)
# Build a Graph that computes the logits predictions from the
# inference model.
#logits1= drd.inference(images, FLAGS.n_residual_blocks)
logits = drd.resnet_v1_50(images)
val_logits = drd.resnet_v1_50(val_images)
# calculate predictions
predictions = tf.cast(tf.argmax(logits, axis=1), tf.int32)
val_predictions = tf.cast(tf.argmax(val_logits, axis=1), tf.int32)
# ops for batch accuracy calcultion
correct_prediction = tf.equal(predictions, labels)
val_correct_prediction = tf.equal(val_predictions, labels)
batch_accuracy = tf.reduce_mean(tf.cast(correct_prediction,
tf.float32))
val_batch_accuracy = tf.reduce_mean(
tf.cast(val_correct_prediction, tf.float32))
# calculate training accuracy
# Calculate loss.
loss = drd.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = drd.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.global_variables())
variables = slim.get_variables_to_restore()
variables_to_restore = [
v for v in variables if not v.name.split('/')[-1] != 'weights:0'
]
# Add ops to save and restore all the variables.
saver_pre = tf.train.Saver(
variables_to_restore[0:-2]) # exclude logits layer
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# # Build an initialization operation to run below.
init = tf.global_variables_initializer()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
# sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(FLAGS.save_dir, sess.graph)
step_start = 0
try:
####Trying to find last checkpoint file fore full final model exist###
print("Trying to restore last checkpoint ...")
save_dir = FLAGS.save_dir
# Use TensorFlow to find the latest checkpoint - if any.
last_chk_path = tf.train.latest_checkpoint(checkpoint_dir=save_dir)
# Try and load the data in the checkpoint.
saver.restore(sess, save_path=last_chk_path)
# If we get to this point, the checkpoint was successfully loaded.
print("Restored checkpoint from:", last_chk_path)
# get the step integer from restored path to start step from there
step_start = int(
filter(
str.isdigit,
unicodedata.normalize('NFKD', last_chk_path).encode(
'ascii', 'ignore')))
except:
# If all the above failed for some reason, simply
# initialize all the variables for the TensorFlow graph.
print(
"Failed to restore any checkpoints. Initializing variables instead."
)
sess.run(init)
accuracy_dev = []
val_accuracy_dev = []
for step in xrange(step_start, FLAGS.max_steps):
start_time = time.time()
_, loss_value, accuracy = sess.run(
[train_op, loss, batch_accuracy])
#im, lab,log = sess.run([images,labels,logits])
#append the next accuray to the development list
accuracy_dev.append(accuracy)
#print([lab,log])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
im_id, val_acc = sess.run([names, val_batch_accuracy])
val_accuracy_dev.append(val_acc)
print("the image being trained on is {}".format(im_id))
print("The average validation accuracy is: {}".format(
np.mean(val_accuracy_dev)))
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = (
'%s: step %d, loss = %.2f, avg_batch_accuracy = %.2f, (%.1f examples/sec; %.3f '
'sec/batch)')
# take averages of all the accuracies from the previous bathces
print(format_str %
(datetime.now(), step, loss_value, np.mean(accuracy_dev),
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 100 == 0 or (step + 1) == FLAGS.max_steps:
#set paths and saving ops for the full and sub_network
checkpoint_path = os.path.join(FLAGS.save_dir, 'model.ckpt')
#pre_trained_path = os.path.join(FLAGS.pre_trained_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def train():
#for which data set to use
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False, name='global_step')
# Get images and labels
images, labels = drd.distorted_inputs()
#get validation data
val_images, val_labels = drd.inputs(False)
#get drop out probability
print(images.get_shape(), val_images.get_shape())
#logits1= drd.inference(images, FLAGS.n_residual_blocks)
logits = model_2.inference(images,
n=4,
reuse=tf.AUTO_REUSE,
is_training=True)
val_logits = model_2.inference(images,
n=4,
reuse=tf.AUTO_REUSE,
is_training=False)
#logits = drd.resnet_v1_50(images, training=True)
#val_logits = drd.resnet_v1_50(val_images, training = False)
#softmx logits
soft_max_logits = tf.nn.softmax(logits)
soft_max_logits_val = tf.nn.softmax(val_logits)
# calculate predictions
predictions = tf.cast(tf.argmax(soft_max_logits, axis=1), tf.int32)
val_predictions = tf.cast(tf.argmax(soft_max_logits_val, axis=1),
tf.int32)
# ops for batch accuracy calcultion
correct_prediction = tf.equal(predictions, labels)
val_correct_prediction = tf.equal(val_predictions, labels)
batch_accuracy = tf.reduce_mean(tf.cast(correct_prediction,
tf.float32))
val_batch_accuracy = tf.reduce_mean(
tf.cast(val_correct_prediction, tf.float32))
# Calculate loss, which includes softmax cross entropy and L2 regularization.
cross_entropy = tf.losses.sparse_softmax_cross_entropy(logits=logits,
labels=labels)
# Create a tensor named cross_entropy for logging purposes.
tf.identity(cross_entropy, name='cross_entropy')
tf.summary.scalar('cross_entropy', cross_entropy)
# If no loss_filter_fn is passed, assume we want the default behavior,
# which is that batch_normalization variables are excluded from loss.
def exclude_batch_norm(name):
return 'batch_normalization' not in name
loss_filter_fn = None or exclude_batch_norm
# Add weight decay to the loss.
l2_loss = weight_decay * tf.add_n(
# loss is computed using fp32 for numerical stability.
[
tf.nn.l2_loss(tf.cast(v, tf.float32))
for v in tf.trainable_variables() if loss_filter_fn(v.name)
])
tf.summary.scalar('l2_loss', l2_loss)
loss = cross_entropy + l2_loss
global_step = tf.train.get_or_create_global_step()
#list of lr decay factors
lr_decay_factors = [1, 0.1, 0.01, 0.001, 0.0001]
learning_rate = 0.001
# Create a tensor named learning_rate for logging purposes
tf.identity(learning_rate, name='learning_rate')
tf.summary.scalar('learning_rate', learning_rate)
optimizer = tf.train.MomentumOptimizer(learning_rate=learning_rate,
momentum=momentum)
minimize_op = optimizer.minimize(loss, global_step)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
train_op = tf.group(minimize_op, update_ops)
# calculate training accuracy
# Calculate loss.
#loss = drd.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
#train_op = drd.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.global_variables())
#variables = slim.get_variables_to_restore()
#variables_to_restore = [v for v in variables if not v.name.split('/')[-1] != 'weights:0']
# Add ops to save and restore all the variables.
#saver_pre = tf.train.Saver(variables_to_restore[0:-2]) # exclude logits layer
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# # Build an initialization operation to run below.
init = tf.global_variables_initializer()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
# sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(FLAGS.save_dir, sess.graph)
step_start = 0
try:
####Trying to find last checkpoint file fore full final model exist###
print("Trying to restore last checkpoint ...")
save_dir = FLAGS.save_dir
# Use TensorFlow to find the latest checkpoint - if any.
last_chk_path = tf.train.latest_checkpoint(checkpoint_dir=save_dir)
# Try and load the data in the checkpoint.
saver.restore(sess, save_path=last_chk_path)
# If we get to this point, the checkpoint was successfully loaded.
print("Restored checkpoint from:", last_chk_path)
# get the step integer from restored path to start step from there
uninitialized_vars = []
for var in tf.global_variables():
try:
sess.run(var)
except tf.errors.FailedPreconditionError:
print("not init")
print(var)
uninitialized_vars.append(var)
# create init op for the still unitilized variables
init_new_vars_op = tf.variables_initializer(uninitialized_vars)
sess.run(init_new_vars_op)
except:
# If all the above failed for some reason, simply
# initialize all the variables for the TensorFlow graph.
print(
"Failed to restore any checkpoints. Initializing variables instead."
)
sess.run(init)
accuracy_dev = []
val_accuracy_dev = []
step_start = 0
for step in range(step_start, FLAGS.max_steps):
start_time = time.time()
#run train op
_, loss_value, accuracy, gs = sess.run(
[train_op, loss, batch_accuracy, global_step])
#setting up a learning rate decay scheme
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 30:
learning_rate = learning_rate * lr_decay_factors[1]
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 60:
learning_rate = learning_rate * lr_decay_factors[2]
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 90:
learning_rate = learning_rate * lr_decay_factors[3]
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 120:
learning_rate = learning_rate * lr_decay_factors[4]
accuracy_dev.append(accuracy)
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
val_acc = sess.run([val_batch_accuracy])
val_accuracy_dev.append(val_acc)
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = (
'%s: step %d, loss = %.2f, avg_batch_accuracy = %.2f, (%.1f examples/sec; %.3f '
'sec/batch), validation accuracy %.2f')
# take averages of all the accuracies from the previous bathces
print(format_str % (datetime.now(), step, loss_value,
np.mean(accuracy_dev), examples_per_sec,
sec_per_batch, np.mean(val_accuracy_dev)))
if step % 10 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 100 == 0 or (step + 1) == FLAGS.max_steps:
#set paths and saving ops for the full and sub_network
checkpoint_path = os.path.join(FLAGS.save_dir, 'model.ckpt')
#pre_trained_path = os.path.join(FLAGS.pre_trained_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False, name='global_step')
# Get images and labels for CIFAR-10.
images, labels, names = drd.distorted_inputs()
# get validation data
val_images, val_labels = drd.inputs(True)
# Build a Graph that computes the logits predictions from the
# inference model.
#logits1= drd.inference(images, FLAGS.n_residual_blocks)
logits = drd.shallow_oxford_net_C(images)
val_logits = drd.shallow_oxford_net_C(val_images)
# calculate predictions
predictions = tf.cast(tf.argmax(logits, axis=1), tf.int32)
val_predictions = tf.cast(tf.argmax(val_logits, axis=1), tf.int32)
# ops for batch accuracy calcultion
correct_prediction = tf.equal(predictions, labels)
val_correct_prediction = tf.equal(val_predictions, labels)
batch_accuracy = tf.reduce_mean(tf.cast(correct_prediction,
tf.float32))
val_batch_accuracy = tf.reduce_mean(
tf.cast(val_correct_prediction, tf.float32))
tf.summary.scalar("Training Accuracy", batch_accuracy)
# Calculate loss.
loss = drd.loss(logits, labels)
# updates the model parameters.
train_op = drd.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.global_variables())
sub_network = 'oxford_net'
#saver_30 = tf.train.Saver(tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=sub_network))
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
#Build an initialization operation to run below.
init = tf.global_variables_initializer()
#Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(FLAGS.train_dir, sess.graph)
step_start = 0
try:
####Trying to find last checkpoint file fore full final model exist###
print("Trying to restore last checkpoint ...")
save_dir = FLAGS.save_dir
# Use TensorFlow to find the latest checkpoint - if any.
last_chk_path = tf.train.latest_checkpoint(checkpoint_dir=save_dir)
# Try and load the data in the checkpoint.
saver.restore(sess, save_path=last_chk_path)
# If we get to this point, the checkpoint was successfully loaded.
print("Restored checkpoint from:", last_chk_path)
uninitialized_vars = []
for var in tf.global_variables():
try:
sess.run(var)
except tf.errors.FailedPreconditionError:
uninitialized_vars.append(var)
# create init op for the still unitilized variables
init_new_vars_op = tf.variables_initializer(uninitialized_vars)
sess.run(init_new_vars_op)
# get the step integer from restored path to start step from there
step_start = int(
filter(
str.isdigit,
unicodedata.normalize('NFKD', last_chk_path).encode(
'ascii', 'ignore')))
except:
# If all the above failed for some reason, simply
# initialize all the variables for the TensorFlow graph.
print(
"Failed to restore any checkpoints. Initializing variables instead."
)
sess.run(init)
names_iterated = []
accuracy_dev = []
val_accuracy_dev = []
for step in xrange(step_start, FLAGS.max_steps):
start_time = time.time()
_, loss_value, accuracy, names_strings = sess.run(
[train_op, loss, batch_accuracy, names])
#append the next accuray to the development list
accuracy_dev.append(accuracy)
names_iterated.append(names_strings)
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
im_id, val_acc = sess.run([names, val_batch_accuracy])
val_accuracy_dev.append(val_acc)
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = (
'%s: step %d, loss = %.2f, avg_batch_accuracy = %.2f, (%.1f examples/sec; %.3f '
'sec/batch), validation accuracy %.2f, image_name: %s')
# take averages of all the accuracies from the previous bathces
print(format_str %
(datetime.now(), step, loss_value, np.mean(accuracy_dev),
examples_per_sec, sec_per_batch,
np.mean(val_accuracy_dev), im_id))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 100 == 0 or (step + 1) == FLAGS.max_steps:
#set paths and saving ops for the full and sub_network
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
pre_trained_path = os.path.join(FLAGS.pre_trained_dir,
'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
#saver_30.save(sess, pre_trained_path, global_step=step)
#write files to disk to verify input pipeline is correct
f = open("file_names_" + str(step), "w")
f.write("\n".join(map(lambda x: str(x), names_iterated)))
f.close()
names_iterated = []